Facial video age progression considering expression change

Shintaro Yamamoto, Pavel A. Savkin, Takuya Kato, Shoichi Furukawa, Shigeo Morishima

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes an age progression method for facial videos. Age is one of the main factors that changes the appearance of the face, due to the associated sagging, spots, and wrinkles. These aging features change in appearance depending on facial expressions. As an example, we see wrinkles appear in the face of the young when smiling, but the shape of wrinkles changes in older faces. Previous work has not considered the temporal changes of the face, using only static images as databases. To solve this problem, we extend the texture synthesis approach to use facial videos as source videos. First, we spatio-temporally align the videos of database to match the sequence of a target video. Then, we synthesize an aging face and apply the temporal changes of the target age to the wrinkles appearing in the facial expression image in the target video. As a result, our method successfully generates expression changes specific to the target age.

Original languageEnglish
Title of host publicationCGI 2017 - Proceedings of the 2017 Computer Graphics International Conference
PublisherAssociation for Computing Machinery
VolumePart F128640
ISBN (Electronic)9781450352284
DOIs
Publication statusPublished - 2017 Jun 27
Externally publishedYes
Event2017 Computer Graphics International Conference, CGI 2017 - Yokohama, Japan
Duration: 2017 Jun 272017 Jun 30

Other

Other2017 Computer Graphics International Conference, CGI 2017
CountryJapan
CityYokohama
Period17/6/2717/6/30

Fingerprint

Aging of materials
Textures

Keywords

  • Age progression
  • Facial video
  • Video editing

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Yamamoto, S., Savkin, P. A., Kato, T., Furukawa, S., & Morishima, S. (2017). Facial video age progression considering expression change. In CGI 2017 - Proceedings of the 2017 Computer Graphics International Conference (Vol. Part F128640). [a5] Association for Computing Machinery. https://doi.org/10.1145/3095140.3095145

Facial video age progression considering expression change. / Yamamoto, Shintaro; Savkin, Pavel A.; Kato, Takuya; Furukawa, Shoichi; Morishima, Shigeo.

CGI 2017 - Proceedings of the 2017 Computer Graphics International Conference. Vol. Part F128640 Association for Computing Machinery, 2017. a5.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yamamoto, S, Savkin, PA, Kato, T, Furukawa, S & Morishima, S 2017, Facial video age progression considering expression change. in CGI 2017 - Proceedings of the 2017 Computer Graphics International Conference. vol. Part F128640, a5, Association for Computing Machinery, 2017 Computer Graphics International Conference, CGI 2017, Yokohama, Japan, 17/6/27. https://doi.org/10.1145/3095140.3095145
Yamamoto S, Savkin PA, Kato T, Furukawa S, Morishima S. Facial video age progression considering expression change. In CGI 2017 - Proceedings of the 2017 Computer Graphics International Conference. Vol. Part F128640. Association for Computing Machinery. 2017. a5 https://doi.org/10.1145/3095140.3095145
Yamamoto, Shintaro ; Savkin, Pavel A. ; Kato, Takuya ; Furukawa, Shoichi ; Morishima, Shigeo. / Facial video age progression considering expression change. CGI 2017 - Proceedings of the 2017 Computer Graphics International Conference. Vol. Part F128640 Association for Computing Machinery, 2017.
@inproceedings{70ac777bb72d4577b1806dceb3d59ffa,
title = "Facial video age progression considering expression change",
abstract = "This paper proposes an age progression method for facial videos. Age is one of the main factors that changes the appearance of the face, due to the associated sagging, spots, and wrinkles. These aging features change in appearance depending on facial expressions. As an example, we see wrinkles appear in the face of the young when smiling, but the shape of wrinkles changes in older faces. Previous work has not considered the temporal changes of the face, using only static images as databases. To solve this problem, we extend the texture synthesis approach to use facial videos as source videos. First, we spatio-temporally align the videos of database to match the sequence of a target video. Then, we synthesize an aging face and apply the temporal changes of the target age to the wrinkles appearing in the facial expression image in the target video. As a result, our method successfully generates expression changes specific to the target age.",
keywords = "Age progression, Facial video, Video editing",
author = "Shintaro Yamamoto and Savkin, {Pavel A.} and Takuya Kato and Shoichi Furukawa and Shigeo Morishima",
year = "2017",
month = "6",
day = "27",
doi = "10.1145/3095140.3095145",
language = "English",
volume = "Part F128640",
booktitle = "CGI 2017 - Proceedings of the 2017 Computer Graphics International Conference",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - Facial video age progression considering expression change

AU - Yamamoto, Shintaro

AU - Savkin, Pavel A.

AU - Kato, Takuya

AU - Furukawa, Shoichi

AU - Morishima, Shigeo

PY - 2017/6/27

Y1 - 2017/6/27

N2 - This paper proposes an age progression method for facial videos. Age is one of the main factors that changes the appearance of the face, due to the associated sagging, spots, and wrinkles. These aging features change in appearance depending on facial expressions. As an example, we see wrinkles appear in the face of the young when smiling, but the shape of wrinkles changes in older faces. Previous work has not considered the temporal changes of the face, using only static images as databases. To solve this problem, we extend the texture synthesis approach to use facial videos as source videos. First, we spatio-temporally align the videos of database to match the sequence of a target video. Then, we synthesize an aging face and apply the temporal changes of the target age to the wrinkles appearing in the facial expression image in the target video. As a result, our method successfully generates expression changes specific to the target age.

AB - This paper proposes an age progression method for facial videos. Age is one of the main factors that changes the appearance of the face, due to the associated sagging, spots, and wrinkles. These aging features change in appearance depending on facial expressions. As an example, we see wrinkles appear in the face of the young when smiling, but the shape of wrinkles changes in older faces. Previous work has not considered the temporal changes of the face, using only static images as databases. To solve this problem, we extend the texture synthesis approach to use facial videos as source videos. First, we spatio-temporally align the videos of database to match the sequence of a target video. Then, we synthesize an aging face and apply the temporal changes of the target age to the wrinkles appearing in the facial expression image in the target video. As a result, our method successfully generates expression changes specific to the target age.

KW - Age progression

KW - Facial video

KW - Video editing

UR - http://www.scopus.com/inward/record.url?scp=85025435132&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85025435132&partnerID=8YFLogxK

U2 - 10.1145/3095140.3095145

DO - 10.1145/3095140.3095145

M3 - Conference contribution

VL - Part F128640

BT - CGI 2017 - Proceedings of the 2017 Computer Graphics International Conference

PB - Association for Computing Machinery

ER -